Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches.

BACKGROUND: The novel coronavirus disease 2019 (COVID-19) constitutes a public health emergency globally. The number of infected people and deaths are proliferating every day, which is putting tremendous pressure on our social and healthcare system. Rapid detection of COVID-19 cases is a significant step to fight against this virus as well as release pressure off the healthcare system. OBJECTIVE: One of the critical factors behind the rapid spread of COVID-19 pandemic is a lengthy clinical testing time. The imaging tool, such as Chest X-ray (CXR), can speed up the identification process. Therefore, our objective is to develop an automated CAD system for the detection of COVID-19 samples from healthy and pneumonia cases using CXR images. METHODS: Due to the scarcity of the COVID-19 benchmark dataset, we have employed deep transfer learning techniques, where we examined 15 different pre-trained CNN models to find the most suitable one for this task. RESULTS: A total of 860 images (260 COVID-19 cases, 300 healthy and 300 pneumonia cases) have been employed to investigate the performance of the proposed algorithm, where 70% images of each class are accepted for training, 15% is used for validation, and rest is for testing. It is observed that the VGG19 obtains the highest classification accuracy of 89.3% with an average precision, recall, and F1 score of 0.90, 0.89, 0.90, respectively. CONCLUSION: This study demonstrates the effectiveness of deep transfer learning techniques for the identification of COVID-19 cases using CXR images.

Immobilization of a novel cold active esterase onto Fe3O4∼cellulose nano-composite enhances catalytic properties.

A novel esterase, EstH was cloned, purified and characterized from the marine bacterium Zunongwangia sp. The purified EstH showed optimum activity at 30°C and pH 8.5 with ∼50% of original activity at 0°C. EstH was stable in high salt conditions (0-4.5M NaCl). To improve the characteristics and explore the possibilities for application, a new immobilization matrix, Fe3O4∼cellulose nano-composite, was prepared and was characterized by Fourier Transform Infrared Spectroscopy (FTIR) and Scanning Electron Microscope (SEM). Interestingly the optimal temperature of immobilized EstH elevated to 35°C. Compared to its free form, immobilized EstH showed better temperature stability (48.5% compared to 22.40% at 50°C after 30min), prolonged half-life (32h compared to 18h), higher storage stability (∼71% activity compared to ∼40% after 50days of storage), improved pH tolerance (∼73% activity at pH 4 and 10), and, more importantly, reusability (∼50% activity after 8 repetitive cycles of usage). Enzyme kinetics showed an increase in the Vmax (from 35.76 to 51.14µM/min) and Kcat (from 365s(-1) to 520s(-1)) after immobilization. The superior catalytic properties of immobilized EstH suggest its great potential in biotechnology and industrial processes.

Characterization of a novel cold active and salt tolerant esterase from Zunongwangia profunda.

A novel cold active esterase, EstLiu was cloned from the marine bacterium Zunongwangia profunda, overexpressed in E. coli BL21 (DE3) and purified by glutathione-S transferase (GST) affinity chromatography. The mature esterase EstLiu sequence encodes a protein of 273 amino acids residues, with a predicted molecular weight of 30KDa and containing the classical pentapeptidase motif from position 156 to 160 with the catalytic triad Ser158-Asp211-His243. Although, EstLiu showed 64% similarity with the hypothetical esterase from Chryseobacterium sp. StRB126 (WP_045498424), phylogenetic analysis showed it had no similarity with any of the established family of lipases/esterases, suggesting that it could be considered as a new family. The purified enzyme showed broad substrate specificity with the highest hydrolytic activity against p-nitrophenyl butyrate (C4). EstLiu showed remarkable activity (75%) at 0°Cand the optimal activity at pH 8.0 and 30°C with good thermostability and quickened inactivation above 60°C. EstLiu retained 81, 103, 67 and 78% of its original activity at 50% (v/v) in ethanol, isopropanol, DMSO and ethylene glycol, respectively. In the presence of Tween 20, Tween 80 and Triton X-100, EstLiu showed 88, 100 and 117% of relative activity. It is also co-factor independent. The high activity at low temperature and desirable stability in organic solvents and salts of this novel family esterase represents a good evidence of novel biocatalyst. Overall, this novel enzyme showed better activity than previously reported esterases in extreme reaction conditions and could promote the reaction in both aqueous and non-aqueous conditions, indicating its great potential for industrial applications.